INDEX
Explanations
words related to geographical features, particularly continents
mentions of continents and their associated characteristics or metrics
New Auto-Interp
Negative Logits
chel
-0.83
externalToEVAOnly
-0.77
ilts
-0.76
aban
-0.76
verbs
-0.72
edi
-0.71
ylene
-0.71
dos
-0.71
ibur
-0.68
aida
-0.67
POSITIVE LOGITS
Continent
1.02
continent
0.94
inian
0.84
alogy
0.76
arium
0.75
continents
0.75
wide
0.75
shores
0.71
inia
0.67
explorer
0.66
Activations Density 0.011%